© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    convert image data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     खाई
    0.98
    ruptedException
    0.86
    Alpine
    0.82
     Potts
    0.80
    好处
    0.80
    baden
    0.80
     घाटी
    0.79
    烙
    0.79
     Piedmont
    0.78
     Milford
    0.78
    POSITIVE LOGITS
     MATLAB
    1.24
     Matlab
    1.16
     cell
    1.11
     %#
    1.07
     ~=
    1.07
     Cells
    1.05
     Cell
    1.02
     matlab
    1.02
    endom
    1.00
     cells
    1.00
    Activations Density 0.006%

    No Known Activations